Reliability Characteristics of Quadratic Hebbian-Type Associative Memories in Optical and Electronic Network Implementations

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)

Abstract

The performance capability of quadratic Hebbian- type associative memories (QHAMs) in the presence of interconnection faults is examined, and equations for predicting the probability of direct convergence Pdcgiven a fraction of interconnection faults are developed. The interconnection faults considered are the equivalent of open-circuit and short-circuit synaptic interconnections in electronic implementations. Our results show that a network with open-circuit interconnection faults has a higher probability of direct convergence Pjcthan a network with short-circuit interconnection faults, when the fraction of failed interconnections p is small and the short-circuit signal G is large. Certain values of G are found to have only mild effects on network performance degradation. Network reliability characteristics taking the generalization capability into account are also analyzed. All of these results are compared with those of Hebbian-type associative memories (HAMs), which have linear association network models. Our results indicate that QHAMs have much higher network capacity and fault-tolerance capability in the presence of interconnection faults. However, the fault tolerance to input errors in QHAMs is much less than that of HAMs.

Original languageEnglish
Pages (from-to)357-367
Number of pages11
JournalIEEE Transactions on Neural Networks
Volume6
Issue number2
DOIs
Publication statusPublished - 1995 Mar

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Reliability Characteristics of Quadratic Hebbian-Type Associative Memories in Optical and Electronic Network Implementations'. Together they form a unique fingerprint.

Cite this